C# Image.DetectHaarCascade方法代码示例

        public Image<Bgr, Byte> FaceDetection(Image Image)
        {
            face = new HaarCascade("haarcascade_frontalface_default.xml");
            Utility UTl = new Utility();

            //Get the current frame form capture device
            Image<Bgr, Byte> currentFrame = UTl.ImageToBgrByte(Image);

            //Convert it to Grayscale
            gray = currentFrame.Convert<Gray, Byte>();

            //Face Detector
            MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(face,1.2,10,Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,new Size(20, 20));

            //Action for element detected
            try
            {
                MCvAvgComp f = facesDetected[0][0];

            result = currentFrame.Copy(f.rect).Convert<Gray, byte>().Resize(100, 100, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
            //draw the face detected in the 0th (gray) channel with blue color
            currentFrame.Draw(f.rect, new Bgr(Color.White), 2);
            }
            catch (Exception ex)
            {
                MessageBox.Show("Camera Error: Empty frames arrived" + ex.Message.ToString(), "Error", MessageBoxButtons.OK, MessageBoxIcon.Error);

            }
            return currentFrame;
        }

        void FrameGrabber(object sender, EventArgs e)
        {
            //Numero inicial de rostros detectados
            label3.Text = "0";

            //Obtener el frame actual desde el disposiivo
            currentFrame = grabber.QueryFrame().Resize(425, 322, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);

            //Convertir el frame a escala de grises
            gray = currentFrame.Convert<Gray, Byte>();

            //Detector de Rostros
            MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(
              face,
              1.2,
              10,
              Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
              new Size(20, 20));

            //Dibujar el ROI para cada rostro detectado
            foreach (MCvAvgComp f in facesDetected[0])
            {
                //Dibujar el ROI de color para identificar el rostro detectado
                currentFrame.Draw(f.rect, new Bgr(Color.OrangeRed), 2);

                //Colocar el numero actual de rostros detectados
                label3.Text = facesDetected[0].Length.ToString();

                //Ajustar el ROI para la detección de los ojos

                gray.ROI = f.rect;
                MCvAvgComp[][] eyesDetected = gray.DetectHaarCascade(
                   eye,
                   1.1,
                   10,
                   Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
                   new Size(20, 20));
                gray.ROI = Rectangle.Empty;

                foreach (MCvAvgComp ey in eyesDetected[0])
                {
                    Rectangle eyeRect = ey.rect;
                    eyeRect.Offset(f.rect.X, f.rect.Y);
                    currentFrame.Draw(eyeRect, new Bgr(Color.Green), 2);
                }
            }

            //Mostrar el video procesado
            imageBoxFrameGrabber.Image = currentFrame;
        }

    public void Detect(byte[] pixels, int width, int height) {

      // Build Image
      Bitmap bitmap = WSRKinectSensor.ToBitmap(pixels, width, height, PixelFormat.Format32bppRgb);
      Image<Bgr, Byte> color = new Image<Bgr, Byte>(bitmap);

      // Convert it to Grayscale
      Gray = color.Convert<Gray, Byte>();

      // Detect faces
      Faces = Gray.DetectHaarCascade(haarCascade, 1.2, 2, Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING, new Size(80, 80))[0];

      // Train if needed
      Train();
    }

        private static void DetectAndDrawEyes(Image<Bgr, byte> image, Image<Gray, byte> gray, MCvAvgComp f, HaarCascade eye)
        {
            gray.ROI = f.rect;
            MCvAvgComp[][] eyesDetected = gray.DetectHaarCascade(
                eye,
                1.1,
                10,
                Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
                new Size(20, 20));
            gray.ROI = Rectangle.Empty;

            foreach (MCvAvgComp e in eyesDetected[0])
            {
                Rectangle eyeRect = e.rect;
                eyeRect.Offset(f.rect.X, f.rect.Y);
                image.Draw(eyeRect, new Bgr(Color.Red), 2);
            }
        }

        // FaceDetection in the normal way
        public override void DoNormalDetection(string imagePath)
        {
            _image = new Image<Bgr, byte>(imagePath); //Read the files as an 8-bit Bgr image  
            _egray = _image.Convert<Gray, Byte>(); //Convert it to Grayscale
            _gray = _egray.Copy();    // Copy image in Grayscale            
            _egray._EqualizeHist(); // Equalize
            Image<Gray, Byte> tempgray = _egray.Copy();

            MCvAvgComp[][] facesDetected = _egray.DetectHaarCascade(_faces, 1.1, 1, Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING, new System.Drawing.Size(20, 20));


            foreach (MCvAvgComp f in facesDetected[0])
            {
                if (f.neighbors > 100)
                {
                    //_image.Draw(f.rect, new Bgr(System.Drawing.Color.Blue), 2); // face
                    tempgray.ROI = f.rect; //Set the region of interest on the faces
                    MCvAvgComp[][] eyesDetected = tempgray.DetectHaarCascade(_eyes, 1.1, 1, Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING, new System.Drawing.Size(20, 20));
                    if (eyesDetected[0].Length != 0)
                    {
                        foreach (MCvAvgComp e in eyesDetected[0])
                        {
                            if (e.neighbors > 100)
                            {
                                System.Drawing.Rectangle eyeRect = e.rect;
                                eyeRect.Offset(f.rect.X, f.rect.Y);
                                _image.Draw(eyeRect, new Bgr(System.Drawing.Color.Red), 2);
                            }
                        }
                    }

                }
            }

            this._processedImages = new IImage[3];
            this._processedImages[0] = _gray;
            this._processedImages[1] = _egray;
            this._processedImages[2] = _image;

        }

        private bool DoEyesRegionExtraction(Image<Gray, Byte> input, TrackData trackData)
        {
            // We assume there's only one face in the video
            MCvAvgComp[][] facesDetected = input.DetectHaarCascade(
                haarCascade,
                Settings.Instance.Eyestracker.ScaleFactor,
                2, //Min. neighbours, higher value reduces false detection
                HAAR_DETECTION_TYPE.FIND_BIGGEST_OBJECT,
                Settings.Instance.Eyestracker.SizeMin);

            if (facesDetected[0].Length == 1)
            {
                MCvAvgComp face = facesDetected[0][0];

                if (face.rect.X != 0 && face.rect.Width != 0)
                {
                    if (face.rect.Height < 100)
                        return false;

                    roiEyes = face.rect;
                    // Add some margin
                    //roiEyes.Y = Convert.ToInt32(roiEyes.Y * 0.90);
                    roiEyes.X = Convert.ToInt32(roiEyes.X*0.85);
                    roiEyes.Height = Convert.ToInt32(roiEyes.Height*1.2);
                    roiEyes.Width = Convert.ToInt32(roiEyes.Width*1.4);
                    foundEyes = true;
                    trackData.EyesROI = roiEyes;
                }
            }
            else
            {
                foundEyes = false;
                roiEyes = new Rectangle(new Point(0, 0), new Size(0, 0));
            }

            Performance.Now.Stamp("Eyes X:" + roiEyes.X + " Y:" + roiEyes.Y + " W:" + roiEyes.Width + " H:" +
                                  roiEyes.Height);

            return foundEyes;
        }

        public IList<RoI> DetectFaces(Image image, EnumDetectionType detectionType, double scale, int minNeighbors, Size minSize)
        {
            IList<RoI> rois = new List<RoI>();

            // convert to openCV format
            HAAR_DETECTION_TYPE detectionTypeOpenCV = EnumHelper.StringToEnum<HAAR_DETECTION_TYPE>(detectionType.ToString());

            try
            {
                Image<Gray, byte> gray = new Image<Gray, byte>(new Bitmap(image));

                //Face Detector
                MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(
                    face,
                    scale,
                    minNeighbors,
                    detectionTypeOpenCV,
                    minSize
                    );


                // create a RoI object for every detected face
                foreach (MCvAvgComp f in facesDetected[0])
                {
                    RoI roi = new RoI();
                    roi.X = f.rect.X;
                    roi.Y = f.rect.Y;
                    roi.Width = f.rect.Width;
                    roi.Height = f.rect.Height;
                    rois.Add(roi);
                }
            }
            catch 
            {
                throw new FaceDetectionException("Error while detecting faces!");
            }
            return rois;
        }

        public void FillBoxByFace(ImageBox image)
        {
            //Get a gray frame from capture device
            gray = grabber.QueryGrayFrame().Resize(320, 240, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);

            //Face Detector
            MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(face,1.2,10,Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,new Size(20, 20));

            //Action for each element detected
            foreach (MCvAvgComp f in facesDetected[0])
            {
                TrainedFace = currentFrame.Copy(f.rect).Convert<Gray, byte>();
                break;
            }

            //resize face detected image for force to compare the same size with the
            //test image with cubic interpolation type method
            TrainedFace = result.Resize(100, 100, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
            //trainingImages.Add(TrainedFace);
            //labels.Add(textBox1.Text);

            //Show face added in gray scale
            image.Image = TrainedFace;
        }

        void FrameGrabber(object sender, EventArgs e)
        {
            label3.Text = "0";
            //label4.Text = "";
            NamePersons.Add("");

            //mengambil queryFrame dari gambar
            DateTime StarTime = DateTime.Now;
            currentFrame = grabber.QueryFrame().Resize(320, 240, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);

                    //konversi
                    gray = currentFrame.Convert<Gray, Byte>();

                    //yang terdeteksi
                    MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(
                  face,
                  1.2,
                  10,
                  Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
                  new Size(20, 20));

                    //Aksi untuk setiap elemen terdeteksi
                    foreach (MCvAvgComp f in facesDetected[0])
                    {
                        t = t + 1;
                        result = currentFrame.Copy(f.rect).Convert<Gray, byte>().Resize(100, 100, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
                        currentFrame.Draw(f.rect, new Bgr(Color.Red), 2);

                        if (trainingImages.ToArray().Length != 0)
                        {
                        MCvTermCriteria termCrit = new MCvTermCriteria(ContTrain, 0.001);

                        EigenObjectRecognizer recognizer = new EigenObjectRecognizer(
                           trainingImages.ToArray(),
                           labels.ToArray(),
                           3000,
                           ref termCrit);

                        name = recognizer.Recognize(result);

                        currentFrame.Draw(name, ref font, new Point(f.rect.X - 2, f.rect.Y - 2), new Bgr(Color.LightGreen));

                        }

                            NamePersons[t-1] = name;
                            NamePersons.Add("");

                        //jumlah yang terdeteksi
                        label3.Text = facesDetected[0].Length.ToString();

                    }
                        t = 0;

                        //nama yang terdeteksi
                    for (int nnn = 0; nnn < facesDetected[0].Length; nnn++)
                    {
                        names = names + NamePersons[nnn] + ", ";
                    }
                    //tampilan pada imageboxframeGrabber
                    imageBoxFrameGrabber.Image = currentFrame;
                    DateTime endTime = DateTime.Now;
                    textBox2.Text = (endTime - StarTime).ToString();
                    label4.Text = names;
                    names = "";
                    NamePersons.Clear();
        }

        void FrameGrabber(object sender, EventArgs e)
        {
            try
            {
                //  NamePersons.Add("");

                currentFrame = grabber.QueryFrame().Resize(640, 480, INTER.CV_INTER_CUBIC);
                //Convert it to Grayscale
                gray = currentFrame.Convert<Gray, Byte>();
                //Face Detector
                MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(
              face,
              1.1,
              5,
              Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
              new Size(60, 60));

                SoNguoi = 0;
                //Action for each element detected

                foreach (MCvAvgComp f in facesDetected[0])
                {
                    t = t + 1;
                    resultface = currentFrame.Copy(f.rect).Convert<Gray, byte>().Resize(100, 100, INTER.CV_INTER_CUBIC);
                    sf = f.rect.Width / 100.0;

                    //draw the face detected in the 0th (gray) channel with blue color
                    currentFrame.Draw(f.rect, new Bgr(Color.Green), 2);

                    grayf = resultface.Resize(30, 30, INTER.CV_INTER_CUBIC);
                    Bitmap tam = grayf.ToBitmap();
                    //Bitmap tamnewsize = new Bitmap(tam, newsizegb);
                    matrixtam = PCA.image_2_matrix(tam);
                    matrixtam = Radon1.ApdungRadon(matrixtam);//PCA.apDungWaveletGabors(matrixtam, 0, 1.56, 1);
                                                              /////////////////////////////////////////

                    #region detect eye, nose, mouth

                    //phat hien mat
                    //eye detect
                    grayf = resultface;

                    rte.X = 0; rte.Y = 15;
                    rte.Width = 100;
                    rte.Height = 40;
                    graye = grayf.Copy(rte).Convert<Gray, byte>();

                    MCvAvgComp[][] eyesDetected = graye.DetectHaarCascade(
                                                  eye,
                                                 1.02,
                                                  5,
                                                  Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
                                                  new Size(20, 20));

                    int k = 0;
                    foreach (MCvAvgComp es in eyesDetected[0])
                    {

                        rt.X = (int)(sf * es.rect.X) + f.rect.X;
                        rt.Y = (int)(sf * (es.rect.Y + 15)) + (int)((f.rect.Y));
                        rt.Width = (int)(26 * sf);
                        rt.Height = (int)(26 * sf);

                        currentFrame.Draw(rt, new Bgr(Color.Yellow), 2);

                        rt.X = es.rect.X; rt.Y = es.rect.Y + 15;
                        rt.Width = 23;
                        rt.Height = 23;
                        graytam = grayf.Copy(rt).Convert<Gray, byte>();
                        if (rt.X > 50)
                        {
                            this.ibe1.Image = graytam;
                            resulteyeR = graytam;
                        }
                        else
                        if (rt.X <= 50)
                        {
                            this.ibe2.Image = graytam;
                            resulteyeL = graytam;
                        }

                        k++;
                        if (k == 2) break;

                    }

                    ////////////////////////////////////////////////////cat mouth tren grayface
                    rtm.X = 0; rtm.Y = 60;
                    rtm.Width = 100;
                    rtm.Height = 40;
                    grayfm = grayf.Copy(rtm).Convert<Gray, byte>();

                    ////////////////////////////////////////

                    //mouth detector
                    MCvAvgComp[][] mouthsDetected = grayfm.DetectHaarCascade(
                mouth,
                1.1,
                5,
                Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.FIND_BIGGEST_OBJECT,
//.........这里部分代码省略.........

        internal string getFaceTag(Bitmap sourceBmp)
        {
            //Get the current frame form capture device
            currentFrame = new Image<Bgr, byte>(sourceBmp).Resize(320, 240, Emgu.CV.CvEnum.INTER.CV_INTER_LINEAR);

            if (currentFrame != null)
            {
                gray_frame = currentFrame.Convert<Gray, Byte>();

                //Face Detector
                MCvAvgComp[][] facesDetected = gray_frame.DetectHaarCascade(
                    Face,
                    1.2,
                    1,
                    Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
                    new System.Drawing.Size(20, 20));

                foreach (MCvAvgComp f in facesDetected[0])
                {
                    t = t + 1;
                    result = currentFrame.Copy(f.rect).Convert<Gray, byte>().Resize(100, 100, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
                    //draw the face detected in the 0th (gray) channel with blue color
                    //currentFrame.Draw(f.rect, new Bgr(Color.Red), 2);

                    if (trainingImages.ToArray().Length != 0)
                    {
                        //TermCriteria for face recognition with numbers of trained images like maxIteration
                        MCvTermCriteria termCrit = new MCvTermCriteria(ContTrain, 0.001);

                        //Eigen face recognizer
                        EigenObjectRecognizer recognizer = new EigenObjectRecognizer(
                           trainingImages.ToArray(),
                           labels.ToArray(),
                           3000,
                           ref termCrit);

                        name = recognizer.Recognize(result) ;
                        if (!name.Equals("")&&name!=null)
                        {
                            return name;
                        }
                    }
                }
            }
            return "Sanmeet" ;
        }

        public void FrameGrabber(object sender, EventArgs e)
        {
            _lastInfo = new List<HeadInformation>();

            CountOfFacesLabel.Text = "0";
            //label4.Text = "";
            NamePersons.Add("");

            //Get the current frame form capture device
            currentFrame = grabber.QueryFrame().Resize(320, 240, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);

            //Convert it to Grayscale
            gray = currentFrame.Convert<Gray, Byte>();

            //Face Detector
            MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(
              face,
              1.2,
              10,
              Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
              new Size(20, 20));

            //Action for each element detected
            foreach (MCvAvgComp f in facesDetected[0])
            {
                t = t + 1;
                result = currentFrame.Copy(f.rect).Convert<Gray, byte>().Resize(100, 100, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
                //draw the face detected in the 0th (gray) channel with blue color
                currentFrame.Draw(f.rect, new Bgr(Color.Red), 2);

                if (trainingImages.ToArray().Length != 0)
                {
                    //TermCriteria for face recognition with numbers of trained images like maxIteration
                    MCvTermCriteria termCrit = new MCvTermCriteria(ContTrain, 0.001);

                    //Eigen face recognizer
                    EigenObjectRecognizer recognizer = new EigenObjectRecognizer(
                       trainingImages.ToArray(),
                       labels.ToArray(),
                       3000,
                       ref termCrit);

                    name = recognizer.Recognize(result);

                    //Draw the label for each face detected and recognized
                    currentFrame.Draw(name, ref font, new Point(f.rect.X - 2, f.rect.Y - 2), new Bgr(Color.Red));

                }

                NamePersons[t - 1] = name;
                NamePersons.Add("");

                //Set the number of faces detected on the scene
                CountOfFacesLabel.Text = facesDetected[0].Length.ToString();

                //Set the region of interest on the faces

                gray.ROI = f.rect;
                MCvAvgComp[][] eyesDetected = gray.DetectHaarCascade(
                   eye,
                   1.9,
                   5,
                   Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
                   new Size(20, 20));
                gray.ROI = Rectangle.Empty;

                foreach (MCvAvgComp ey in eyesDetected[0])
                {
                    Rectangle eyeRect = ey.rect;
                    eyeRect.Inflate(-7, -7);
                    eyeRect.Offset(f.rect.X, f.rect.Y);
                    currentFrame.Draw(eyeRect, new Bgr(Color.Blue), 2);
                }

                //gray.ROI = f.rect;
                //MCvAvgComp[][] mouthDetected = gray.DetectHaarCascade(
                //   mouth,
                //   1.1,
                //   37,
                //   Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
                //   new Size(20, 20));
                //gray.ROI = Rectangle.Empty;

                //foreach (MCvAvgComp ey in mouthDetected[0])
                //{
                //    Rectangle mouthRect = ey.rect;
                //    mouthRect.Offset(f.rect.X, f.rect.Y);
                //    currentFrame.Draw(mouthRect, new Bgr(Color.Black), 2);
                //}

                gray.ROI = f.rect;
                MCvAvgComp[][] smileDetected = gray.DetectHaarCascade(
                   smile,
                   2,
                   20,
                   Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
                   new Size(20, 20));
                gray.ROI = Rectangle.Empty;

                HeadInformation hi = new HeadInformation();
//.........这里部分代码省略.........

        private void addface_Click(object sender, EventArgs e)
        {
            try
            {
                if (textBox1.Text == "" | loptxt.Text == "" | mssvtxt.Text == "") MessageBox.Show("Chưa nhập đủ thông tin");
                else
                {
                    gray = grabber.QueryGrayFrame().Resize(640, 480, INTER.CV_INTER_CUBIC);

                    //Face Detector
                    MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(
             face,
             1.1,
             5,
             Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.FIND_BIGGEST_OBJECT,
             new Size(60, 60));
                    //Action for each element detected
                    foreach (MCvAvgComp f in facesDetected[0])
                    {
                        //  resultface = currentFrame.Copy(f.rect).Convert<Gray, byte>().Resize(100, 100, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
                        TrainedFace = currentFrame.Copy(f.rect).Convert<Gray, byte>();

                        break;
                    }

                    if (resultface == null) { timer3.Start(); return; }
                    //resize face detected image for force to compare the same size with the
                    //test image with cubic interpolation type method
                    TrainedFace = resultface.Resize(100, 100, INTER.CV_INTER_CUBIC);
                    //them ten va face vao mang

                    //Show face added in gray scale
                    //if (dem == 0)
                    imageBox1.Image = TrainedFace;

                    try
                    {
                        //TrainedFace.Save(directory + "face" + matrix1s.Count + ".bmp");
                        grabber.QueryFrame().Resize(640, 480, INTER.CV_INTER_CUBIC).Save(directory + textBox1.Text + matrix1s.Count + ".bmp");

                    }
                    catch (Exception ex)
                    {
                        for (int i = matrix1s.Count; i < dem; i++)
                        {
                            // File.Delete(directory + "face" + (matrix1s.Count + dem) + ".bmp");
                            File.Delete(directory + textBox1.Text + (matrix1s.Count + dem) + ".bmp");
                        }
                    }

                    //tface.Add(TrainedFace);
                    TrainedFace = TrainedFace.Resize(50, 50, INTER.CV_INTER_CUBIC);

                    Bitmap tam = TrainedFace.ToBitmap();
                    Bitmap bmnewsize = new Bitmap(tam, newsizegb);
                    x = PCA.image_2_matrix(bmnewsize);
                    x = Radon1.ApdungRadon(x);// PCA.apDungWaveletGabors(x, 0, 1.56, 1);
                    matrix1stam.Add(x);
                    matrix1s.Add(x);
                    labels.Add(mssvtxt.Text);

                    if (dem != 9)
                        addface.Text = "Add face " + (dem + 2).ToString();
                    dem++;

                    if (dem == 10)
                    {
                        luuanh();
                        MessageBox.Show(textBox1.Text + "'s Face detected and added :)", "Training OK", MessageBoxButtons.OK, MessageBoxIcon.Information);
                        dem = 0; mauso = 1;
                        // tface = null; tface = new List<Image<Gray, byte>>();
                        matrix1stam = null; matrix1stam = new List<Matrix1>();
                        x = null;
                        imageBox1.Image = null;
                        ibe1.Image = ibe2.Image = ibn.Image = ibm.Image = null;
                        addface.Text = "Add face 1";
                        resultface = resulteyeL = resulteyeR = resultmouth = resultnose = null;
                        refreshdata();

                    }
                    HDfaces++;
                    mauso++;
                    if (HDfaces <= 10)
                    {

                        label9.Text = mauso.ToString();
                        pictureBox1.Image = Image.FromFile(Application.StartupPath.ToString() + "/huongdan/" + HDfaces.ToString() + ".bmp");
                        //MessageBox.Show(HDfaces.ToString());
                    }

                }

            }
            catch (Exception ex)
            {
                dem = 0;
                MessageBox.Show(ex.ToString(), "Training Fail", MessageBoxButtons.OK, MessageBoxIcon.Exclamation);
            }
        }

        public void FrameGrabber2(object sender, EventArgs e)
        {
            NamePersons.Add("");

            face = new HaarCascade("haarcascade_frontalface_default.xml");
            //Utility UTl = new Utility();

            //Get the current frame form capture device
            //Image<Bgr, Byte> currentFrame = UTl.ImageToBgrByte(Image);
            try
            {
                currentFrame = grabber.QueryFrame().Resize(320, 240, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
            }
            catch (Exception exp)
            {
                grabber = new Capture("video002.mp4");
            }
            //Convert it to Grayscale
            gray = currentFrame.Convert<Gray, Byte>();

            //Face Detector
            MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(face, 1.2, 10, Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING, new Size(20, 20));

            //Action for element detected
            try
            {
                MCvAvgComp f = facesDetected[0][0];

                result = currentFrame.Copy(f.rect).Convert<Gray, byte>().Resize(100, 100, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
                //draw the face detected in the 0th (gray) channel with blue color
                currentFrame.Draw(f.rect, new Bgr(Color.White), 2);
            }
            catch (Exception ex)
            {
                //MessageBox.Show("Camera Error: Empty frames arrived" + ex.Message.ToString(), "Error", MessageBoxButtons.OK, MessageBoxIcon.Error);

            }

                if (trainingImages.ToArray().Length != 0)
                {
                    //TermCriteria for face recognition with numbers of trained images like maxIteration
                    MCvTermCriteria termCrit = new MCvTermCriteria(ContTrain, 0.001);

                    //Eigen face recognizer
                    EigenObjectRecognizer recognizer = new EigenObjectRecognizer(
                       trainingImages.ToArray(),
                       labels.ToArray(),
                       3000,
                       ref termCrit);

                    name = recognizer.Recognize(result);

                    //Draw the label for each face detected and recognized
                    //currentFrame.Draw(name, ref font, new Point(f.rect.X - 2, f.rect.Y - 2), new Bgr(Color.LightGreen));

                }

                //NamePersons[t - 1] = name;
                NamePersons.Add("");

            t = 0;

            //Names concatenation of persons recognized
            //for (int nnn = 0; nnn < facesDetected[0].Length; nnn++)
            //{
            //    names = names + NamePersons[nnn] + ", ";
            //}
            //Show the faces procesed and recognized
            emguImgFace.Image = currentFrame;
            lblCandidateID.Text = name;
            name = "";
            //Clear the list(vector) of names
            NamePersons.Clear();
        }

        public void FrameGrabber(object sender, EventArgs e)
        {
            lbl3 = "0";
            lbl4 = "";
            NamePersons.Add("");

            //Get the current frame form capture device
            try
            {
                currentFrame = grabber.QueryFrame().Resize(320, 240, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
            }
            catch { }

            //Convert it to Grayscale
            gray = currentFrame.Convert<Gray, Byte>();

            //Face Detector
            MCvAvgComp[][] facesDetected = gray.DetectHaarCascade(
          face,
          1.2,
          10,
          Emgu.CV.CvEnum.HAAR_DETECTION_TYPE.DO_CANNY_PRUNING,
          new Size(20, 20));

            //Action for each element detected
            foreach (MCvAvgComp f in facesDetected[0])
            {
                t = t + 1;
                result = currentFrame.Copy(f.rect).Convert<Gray, byte>().Resize(100, 100, Emgu.CV.CvEnum.INTER.CV_INTER_CUBIC);
               
                //draw the face detected in the 0th (gray) channel with blue color
                currentFrame.Draw(f.rect, new Bgr(Color.Red), 2);


                if (trainingImages.ToArray().Length != 0)
                {
                    //UpdateRecognizer();
                    name = recognizer.Recognize(new Image<Gray,byte>( ImageProcessing.ImagePreProcessing(result.ToBitmap())));
                    //Draw the label for each face detected and recognized
                    currentFrame.Draw(name, ref font, new Point(f.rect.X - 2, f.rect.Y - 2), new Bgr(Color.LightGreen));
                }

                NamePersons[t - 1] = name;
                NamePersons.Add("");


                //Set the number of faces detected on the scene
                lbl3 = facesDetected[0].Length.ToString();

            }
            t = 0;

            //Names concatenation of persons recognized
            for (int nnn = 0; nnn < facesDetected[0].Length; nnn++)
            {
                names = names + NamePersons[nnn] + ", ";
            }
            //Show the faces procesed and recognized
            pictureBoxFrameGrabber.Image = currentFrame.ToBitmap();
            lbl3 = names;
            names = "";
            //Clear the list(vector) of names
            NamePersons.Clear();
        }